HTML file crashes program

[Pedroski55]

@snippsatt Just trying!

Still not too sure how to jump ahead from the start_pos in this start_pos = pattern1.search(line).span()[1], but I get the result I wanted!

I believe bowlfred is very good with re, maybe he can straighten out my code!

This gets me the desired result. The problem was, the html is not uniform.

I needed another pattern to cater for the lack of alt="

#! /usr/bin/python3
import re
  
path2text = '/home/pedro/temp/lovely_louise.html'
with open(path2text) as f:
    lines = f.readlines()

print('lines is', len(lines), 'long')

# get lines with '<img src="'
data = []
for line in lines:
    if '<img src="' in line:
        data.append(line)

print('data is', len(data), 'long')

for d in data:
    print(d)

pattern1 = re.compile('<img src="')
#pattern2 = re.compile('img src=".jpg"')
pattern2 = re.compile('jpg" alt="')
pattern3 = re.compile('gif" alt="')
pattern4 = re.compile('jpg" border="')

def get_Image_name(line):
    start_span = pattern1.search(line).span()
    start_pos = pattern1.search(line).span()[1]
    # maybe not a jpg
    if not pattern2.search(line) == None:
        end_pos = pattern2.search(line).span()[0] + 3
    elif not pattern3.search(line) == None:
        end_pos = pattern3.search(line).span()[0] + 3
    elif not pattern4.search(line) == None:
        end_pos = pattern4.search(line).span()[0] + 3
    # add more ifs for other images
    img_name = line[start_pos:end_pos]
    return img_name

# a list to take the names
jpg_names = []

# some names are not picked up, need to look at that
for line in data:
    print(line)
    name = get_Image_name(line)
    jpg_names.append(name)

print('jpg_names is', len(jpg_names), 'long')
savename = '/home/pedro/temp/photo_names.txt'

for jpeg in jpg_names:
    print('picture is', jpeg)

with open(savename, 'w') as f:
    text = '\n'.join(jpg_names)
    f.write(text)

print('All done!')